ResearchFusion AI: An Evidence-Grounded Framework for Multi-Paper Research Gap Analysis, Novelty Assessment, and Roadmap Generation

  • Unique Paper ID: 211195
  • Volume: 13
  • Issue: 6
  • PageNo: 3646-3653
  • Abstract:
  • Scientific research requires researchers to compare prior studies before defining a meaningful research problem. This process involves examining methods, datasets, evaluation measures, results, limitations, and future-work statements across multiple papers. This paper proposes ResearchFusion AI, a multi-domain framework designed to support that process for a user-selected collection of three to ten research papers. The framework organizes extracted information into structured records, generates cross-paper comparisons, groups related limitations, and identifies research dimensions that appear underexplored in the supplied corpus. It then produces candidate research directions and a heuristic novelty indicator on a 0–100 scale, based on semantic distance, uncommon combinations of techniques, coverage of selected gaps, and a technical-contribution rubric. A separate feasibility estimate communicates practical constraints. Evidence-linked retrieval and schema-constrained outputs are used to make generated statements traceable to source passages. The paper describes the proposed architecture, six processing modules, a five-phase research roadmap, and an evaluation protocol. A healthcare example illustrates the workflow; it is not an empirical performance result. ResearchFusion AI is intended as a decision-support system, and its generated ideas and novelty estimates require expert review and a broader literature search.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{211195,
        author = {Rohan Gaikwad and Ishita Deepak Shete and Manish Narayan Gholap and Shrikar Amol Dehadray and Aarti Pimpalkar and Mayuresh Gulame},
        title = {ResearchFusion AI: An Evidence-Grounded Framework for Multi-Paper Research Gap Analysis, Novelty Assessment, and Roadmap Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {6},
        pages = {3646-3653},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=211195},
        abstract = {Scientific research requires researchers to compare prior studies before defining a meaningful research problem. This process involves examining methods, datasets, evaluation measures, results, limitations, and future-work statements across multiple papers. This paper proposes ResearchFusion AI, a multi-domain framework designed to support that process for a user-selected collection of three to ten research papers. The framework organizes extracted information into structured records, generates cross-paper comparisons, groups related limitations, and identifies research dimensions that appear underexplored in the supplied corpus. It then produces candidate research directions and a heuristic novelty indicator on a 0–100 scale, based on semantic distance, uncommon combinations of techniques, coverage of selected gaps, and a technical-contribution rubric. A separate feasibility estimate communicates practical constraints. Evidence-linked retrieval and schema-constrained outputs are used to make generated statements traceable to source passages. The paper describes the proposed architecture, six processing modules, a five-phase research roadmap, and an evaluation protocol. A healthcare example illustrates the workflow; it is not an empirical performance result. ResearchFusion AI is intended as a decision-support system, and its generated ideas and novelty estimates require expert review and a broader literature search.},
        keywords = {evidence-grounded generation, large language models, literature review, novelty assessment, research gap analysis, research planning, retrieval-augmented generation},
        month = {November},
        }

Cite This Article

Gaikwad, R., & Shete, I. D., & Gholap, M. N., & Dehadray, S. A., & Pimpalkar, A., & Gulame, M. (2026). ResearchFusion AI: An Evidence-Grounded Framework for Multi-Paper Research Gap Analysis, Novelty Assessment, and Roadmap Generation. International Journal of Innovative Research in Technology (IJIRT), 13(6), 3646–3653.

Related Articles